Similarity as Reward Alignment: Robust and Versatile Preference-based Reinforcement Learning

A new contrastive framework called SARA aims to improve the robustness of preference-based reinforcement learning against noisy or inaccurate human labeling.

Firefly links to the original publisher. The summary above is AI-generated for orientation and may differ from the source. The “current rank score” decays over time so newer significant stories surface first.